Automatic blood vessel segmentation from retinal images plays an important role in the diagnosis of many systemic and eye diseases, including retinopathy of prematurity. Current state-of-the-art research in blood vessel segmentation from retinal images is based on convolutional neural networks. The solutions proposed so far are trained and tested on images from a few available retinal blood vessel segmentation datasets, which might limit their performance when given an image with retinopathy of prematurity signs. In this paper, we evaluate the performance of three high-performing convolutional neural networks for retinal blood vessel segmentation in the context of blood vessel segmentation on retinopathy of prematurity retinal images. The main motive behind the study is to test if existing public datasets suffice to develop a high-performing predictor that could assist an ophthalmologist in retinopathy of prematurity diagnosis. To do so, we create a dataset consisting solely of retinopathy of prematurity images with retinal blood vessel annotations manually labeled by two observers, where one is the ophthalmologist experienced in retinopathy of prematurity treatment. Experimental results show that all three solutions have difficulties in detecting the retinal blood vessels of infants due to a lower contrast compared to images from public datasets as demonstrated by a significant drop in classification sensitivity. All three solutions segment alongside retinal also choroidal blood vessels which are not used to diagnose retinopathy of prematurity, but instead represent noise and are confused with retinal blood vessels. By visual and numerical observations, we observe that existing solutions for retinal blood vessel segmentation need improvement toward more detailed datasets or deeper models in order to assist the ophthalmologist in retinopathy of prematurity diagnosis.
相關內容
Individuals or companies in a large social or financial network often display rather heterogeneous behaviors for various reasons. In this work, we propose a network vector autoregressive model with a latent group structure to model heterogeneous dynamic patterns observed from network nodes, for which group-wise network effects and timeinvariant fixed-effects can be naturally incorporated. In our framework, the model parameters and network node memberships can be simultaneously estimated by minimizing a least-squares type objective function. In particular, our theoretical investigation allows the number of latent groups G to be over-specified when achieving the estimation consistency of the model parameters and group memberships, which significantly improves the robustness of the proposed approach. When G is correctly specified, valid statistical inference can be made for model parameters based on the asymptotic normality of the estimators. A data-driven criterion is developed to consistently identify the true group number for practical use. Extensive simulation studies and two real data examples are used to demonstrate the effectiveness of the proposed methodology.
Deep neural networks are vulnerable to universal adversarial perturbation (UAP), an instance-agnostic perturbation capable of fooling the target model for most samples. Compared to instance-specific adversarial examples, UAP is more challenging as it needs to generalize across various samples and models. In this paper, we examine the serious dilemma of UAP generation methods from a generalization perspective -- the gradient vanishing problem using small-batch stochastic gradient optimization and the local optima problem using large-batch optimization. To address these problems, we propose a simple and effective method called Stochastic Gradient Aggregation (SGA), which alleviates the gradient vanishing and escapes from poor local optima at the same time. Specifically, SGA employs the small-batch training to perform multiple iterations of inner pre-search. Then, all the inner gradients are aggregated as a one-step gradient estimation to enhance the gradient stability and reduce quantization errors. Extensive experiments on the standard ImageNet dataset demonstrate that our method significantly enhances the generalization ability of UAP and outperforms other state-of-the-art methods. The code is available at //github.com/liuxuannan/Stochastic-Gradient-Aggregation.
This paper is devoted to studying the optimal expressive power of ReLU deep neural networks (DNNs) and its application in approximation via the Kolmogorov Superposition Theorem. We first constructively prove that any continuous piecewise linear functions on $[0,1]$, comprising $O(N^2L)$ segments, can be represented by ReLU DNNs with $L$ hidden layers and $N$ neurons per layer. Subsequently, we demonstrate that this construction is optimal regarding the parameter count of the DNNs, achieved through investigating the shattering capacity of ReLU DNNs. Moreover, by invoking the Kolmogorov Superposition Theorem, we achieve an enhanced approximation rate for ReLU DNNs of arbitrary width and depth when dealing with continuous functions in high-dimensional spaces.
Entity Set Expansion (ESE) is a critical task aiming to expand entities of the target semantic class described by a small seed entity set. Most existing ESE methods are retrieval-based frameworks that need to extract the contextual features of entities and calculate the similarity between seed entities and candidate entities. To achieve the two purposes, they should iteratively traverse the corpus and the entity vocabulary provided in the datasets, resulting in poor efficiency and scalability. The experimental results indicate that the time consumed by the retrieval-based ESE methods increases linearly with entity vocabulary and corpus size. In this paper, we firstly propose a generative ESE framework, Generative Entity Set Expansion (GenExpan), which utilizes a generative pre-trained language model to accomplish ESE task. Specifically, a prefix tree is employed to guarantee the validity of entity generation, and automatically generated class names are adopted to guide the model to generate target entities. Moreover, we propose Knowledge Calibration and Generative Ranking to further bridge the gap between generic knowledge of the language model and the goal of ESE task. Experiments on publicly available datasets show that GenExpan is efficient and effective. For efficiency, expansion time consumed by GenExpan is independent of entity vocabulary and corpus size, and GenExpan achieves an average 600% speedup compared to strong baselines. For expansion performance, our framework outperforms previous state-of-the-art ESE methods.
Speech-driven 3D face animation poses significant challenges due to the intricacy and variability inherent in human facial movements. This paper emphasizes the importance of considering both the composite and regional natures of facial movements in speech-driven 3D face animation. The composite nature pertains to how speech-independent factors globally modulate speech-driven facial movements along the temporal dimension. Meanwhile, the regional nature alludes to the notion that facial movements are not globally correlated but are actuated by local musculature along the spatial dimension. It is thus indispensable to incorporate both natures for engendering vivid animation. To address the composite nature, we introduce an adaptive modulation module that employs arbitrary facial movements to dynamically adjust speech-driven facial movements across frames on a global scale. To accommodate the regional nature, our approach ensures that each constituent of the facial features for every frame focuses on the local spatial movements of 3D faces. Moreover, we present a non-autoregressive backbone for translating audio to 3D facial movements, which maintains high-frequency nuances of facial movements and facilitates efficient inference. Comprehensive experiments and user studies demonstrate that our method surpasses contemporary state-of-the-art approaches both qualitatively and quantitatively.
Nucleus image segmentation is a crucial step in the analysis, pathological diagnosis, and classification, which heavily relies on the quality of nucleus segmentation. However, the complexity of issues such as variations in nucleus size, blurred nucleus contours, uneven staining, cell clustering, and overlapping cells poses significant challenges. Current methods for nucleus segmentation primarily rely on nuclear morphology or contour-based approaches. Nuclear morphology-based methods exhibit limited generalization ability and struggle to effectively predict irregular-shaped nuclei, while contour-based extraction methods face challenges in accurately segmenting overlapping nuclei. To address the aforementioned issues, we propose a dual-branch network using hybrid attention based residual U-blocks for nucleus instance segmentation. The network simultaneously predicts target information and target contours. Additionally, we introduce a post-processing method that combines the target information and target contours to distinguish overlapping nuclei and generate an instance segmentation image. Within the network, we propose a context fusion block (CF-block) that effectively extracts and merges contextual information from the network. Extensive quantitative evaluations are conducted to assess the performance of our method. Experimental results demonstrate the superior performance of the proposed method compared to state-of-the-art approaches on the BNS, MoNuSeg, CoNSeg, and CPM-17 datasets.
There is a recently discovered and intriguing phenomenon called Neural Collapse: at the terminal phase of training a deep neural network for classification, the within-class penultimate feature means and the associated classifier vectors of all flat classes collapse to the vertices of a simplex Equiangular Tight Frame (ETF). Recent work has tried to exploit this phenomenon by fixing the related classifier weights to a pre-computed ETF to induce neural collapse and maximize the separation of the learned features when training with imbalanced data. In this work, we propose to fix the linear classifier of a deep neural network to a Hierarchy-Aware Frame (HAFrame), instead of an ETF, and use a cosine similarity-based auxiliary loss to learn hierarchy-aware penultimate features that collapse to the HAFrame. We demonstrate that our approach reduces the mistake severity of the model's predictions while maintaining its top-1 accuracy on several datasets of varying scales with hierarchies of heights ranging from 3 to 12. Code: //github.com/ltong1130ztr/HAFrame
The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large language models has been dramatically improved, leading to human-like performances in understanding, language synthesizing, and common-sense reasoning, etc. Such a major leap-forward in general AI capacity will change the pattern of how personalization is conducted. For one thing, it will reform the way of interaction between humans and personalization systems. Instead of being a passive medium of information filtering, large language models present the foundation for active user engagement. On top of such a new foundation, user requests can be proactively explored, and user's required information can be delivered in a natural and explainable way. For another thing, it will also considerably expand the scope of personalization, making it grow from the sole function of collecting personalized information to the compound function of providing personalized services. By leveraging large language models as general-purpose interface, the personalization systems may compile user requests into plans, calls the functions of external tools to execute the plans, and integrate the tools' outputs to complete the end-to-end personalization tasks. Today, large language models are still being developed, whereas the application in personalization is largely unexplored. Therefore, we consider it to be the right time to review the challenges in personalization and the opportunities to address them with LLMs. In particular, we dedicate this perspective paper to the discussion of the following aspects: the development and challenges for the existing personalization system, the newly emerged capabilities of large language models, and the potential ways of making use of large language models for personalization.
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question answering or machine translation). However, it builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. Moreover, it is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime. The first goal of this thesis is to characterize the different forms this shift can take in the context of natural language processing, and propose benchmarks and evaluation metrics to measure its effect on current deep learning architectures. We then proceed to take steps to mitigate the effect of distributional shift on NLP models. To this end, we develop methods based on parametric reformulations of the distributionally robust optimization framework. Empirically, we demonstrate that these approaches yield more robust models as demonstrated on a selection of realistic problems. In the third and final part of this thesis, we explore ways of efficiently adapting existing models to new domains or tasks. Our contribution to this topic takes inspiration from information geometry to derive a new gradient update rule which alleviate catastrophic forgetting issues during adaptation.
Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor skills as well as to long-term memory consolidation and retrieval. Consequently, lifelong learning capabilities are crucial for autonomous agents interacting in the real world and processing continuous streams of information. However, lifelong learning remains a long-standing challenge for machine learning and neural network models since the continual acquisition of incrementally available information from non-stationary data distributions generally leads to catastrophic forgetting or interference. This limitation represents a major drawback for state-of-the-art deep neural network models that typically learn representations from stationary batches of training data, thus without accounting for situations in which information becomes incrementally available over time. In this review, we critically summarize the main challenges linked to lifelong learning for artificial learning systems and compare existing neural network approaches that alleviate, to different extents, catastrophic forgetting. We discuss well-established and emerging research motivated by lifelong learning factors in biological systems such as structural plasticity, memory replay, curriculum and transfer learning, intrinsic motivation, and multisensory integration.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191